© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 2360
    Prev
    Next
    INDEX
    Explanations

    modern engines, web, electric, upgrade

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ので
    4.30
    お
    4.04
    ن
    3.88
    क
    3.46
    স
    3.45
    ği
    3.32
    го
    2.96
    ছে
    2.95
    ש
    2.95
    ح
    2.90
    POSITIVE LOGITS
    s
    7.88
    ের
    6.41
    sion
    6.22
    ים
    5.54
    ات
    5.48
    ς
    5.24
    ség
    5.13
    ों
    4.70
    tions
    4.68
    tive
    4.61
    Activations Density 0.511%

    No Known Activations